Everything is Connected: Graph Neural Networks

Abstract

In many ways, graphs are the main modality of data we receive from nature. This is due to the fact that most of the patterns we see, both in natural and artificial systems, are elegantly representable using the language of graph structures. Prominent examples include molecules (represented as graphs of atoms and bonds), social networks and transportation networks. This potential has already been seen by key scientific and industrial groups, with already-impacted application areas including traffic forecasting, drug discovery, social network analysis and recommender systems. Further, some of the most successful domains of application for machine learning in previous years -- images, text and speech processing -- can be seen as special cases of graph representation learning, and consequently there has been significant exchange of information between these areas. The main aim of this short survey is to enable the reader to assimilate the key concepts in the area, and position graph representation learning in a proper context with related fields.

To appear in Current Opinion in Structural Biology. 14 pages, 1 figure

References in corpus (2)

• Predicting multicellular function through multi-layer tissue networks
• Drug-Drug Adverse Effect Prediction with Graph Co-Attention

Cited by in corpus (16)

• Opening the Black-Box: A Systematic Review on Explainable AI in Remote Sensing
• The Expressive Power of Graph Neural Networks: A Survey
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• A Comparison Between Invariant and Equivariant Classical and Quantum Graph Neural Networks
• Sampling Theory of Jointly Bandlimited Time-vertex Graph Signals
• Approaching Collateral Optimization for NISQ and Quantum-Inspired Computing
• Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics
• End-to-end Stroke imaging analysis, using reservoir computing-based effective connectivity, and interpretable Artificial intelligence
• Progress in End-to-End Optimization of Detectors for Fundamental Physics with Differentiable Programming
• Enhanced Spatial Clustering of Single-Molecule Localizations with Graph Neural Networks
• A unifying primary framework for quantum graph neural networks from quantum graph states
• EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification
• Community detection robustness of graph neural networks
• Optimal message passing for molecular prediction is simple, attentive and spatial